Runyu Ding

Xian Liu

Xian Liu is a research scientist at NVIDIA Research. He received his Ph.D. in Multi-Media Laboratory (MMLab), The Chinese University of Hong Kong (CUHK) in 2025, where he worked with Prof. Dahua Lin and Prof. Ziwei Liu. His research interests include computer vision and generative models, especially the foundation GenAI (image/video/3D/4D generation), large-scale vision-language models, multi-modal tokenizers, and their applications in digital humans.

Xiaohui Zeng

Yu Fang

Cosmos World Foundation Model Platform for Physical AI

Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a
digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model
Platform to help developers build customized world models for their Physical AI setups. We position
a world foundation model as a general-purpose world model that can be fine-tuned into customized
world models for downstream applications. Our platform covers a video curation pipeline, pre-trained

Julius Berner

Julius Berner is a research scientist in NVIDIA’s Fundamental Generative AI Research (GenAIR) Group. He did his postdoc at Caltech and received his PhD from the University of Vienna in 2023. His research focuses on (probabilistic) machine learning with applications in the natural sciences, including generative modeling, sampling, and neural solvers for partial differential equations and inverse problems. More information can be found on his personal website.

Francesco Ferroni

Loic Magne

Nikita Cherniadev

Automatic Tracing in Task-Based Runtime Systems

Implicitly parallel task-based runtime systems often perform dynamic analysis to discover dependencies in and extract parallelism from sequential programs. Dependence analysis becomes expensive as task granularity drops below a threshold. Tracing techniques have been developed where programmers annotate repeated program fragments (traces) issued by the application, and the runtime system memoizes the dependence analysis for those fragments, greatly reducing overhead when the fragments are executed again.

Subscribe to